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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14169
    Prev
    Next
    INDEX
    Explanations

    hiding or concealing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    közi
    0.46
     you
    0.44
     as
    0.44
     persönlich
    0.42
    賖
    0.42
     persönliche
    0.42
     únicas
    0.42
     sterile
    0.41
     coupons
    0.41
    kon
    0.41
    POSITIVE LOGITS
     hide
    1.22
     hiding
    1.02
    Hide
    0.97
     hid
    0.96
     Hide
    0.96
    hide
    0.95
     esconder
    0.94
     escond
    0.91
     숨
    0.89
    隐藏
    0.89
    Activations Density 0.036%

    No Known Activations