© 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. 189792
    Prev
    Next
    INDEX
    Explanations

    introducing specific contexts or states

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

    recipe channel, highlights systematic

    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
    im
    0.45
     midwifery
    0.44
    ÷
    0.43
    av
    0.43
    ides
    0.42
     \%
    0.42
     pooled
    0.42
     source
    0.41
     %
    0.40
    aries
    0.40
    POSITIVE LOGITS
    меч
    0.54
     renovación
    0.52
    град
    0.50
     transformação
    0.50
     transformación
    0.50
    Alfa
    0.49
    Кли
    0.49
     parceria
    0.49
     acheté
    0.49
     Тол
    0.48
    Activations Density 0.001%

    No Known Activations