© 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. 84594
    Prev
    Next
    INDEX
    Explanations

    outstanding items

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

    freeze Russian assets

    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
    运动员
    0.55
     incroy
    0.51
    ᚄ
    0.49
     enormes
    0.48
     sympathique
    0.48
    ڪ
    0.48
     simplifié
    0.47
     densément
    0.47
     maneiras
    0.46
     enorme
    0.46
    POSITIVE LOGITS
    ↵↵
    0.55
    produced
    0.45
    attacking
    0.44
     due
    0.44
    habilitation
    0.43
    ENER
    0.42
    oting
    0.41
    assed
    0.41
    length
    0.41
    OLD
    0.41
    Activations Density 0.000%

    No Known Activations