© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23096
    Prev
    Next
    INDEX
    Explanations

    accepted version, latest information, inspirational pdf

    np_acts-logits-general · gemini-2.5-flash-lite

    claims, weather, damage, Native, findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revamped
    0.54
     chemins
    0.54
    apprentissage
    0.54
     bodied
    0.54
    г
    0.52
     paced
    0.51
     recreating
    0.51
     tué
    0.50
    ेंटिस
    0.50
     creando
    0.49
    POSITIVE LOGITS
    1
    0.52
     Bien
    0.48
    lateral
    0.45
     Lateral
    0.44
     Lawrence
    0.42
     Warning
    0.42
    frank
    0.42
     Values
    0.42
     Statistical
    0.42
    MENT
    0.41
    Activations Density 0.000%

    No Known Activations