Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 20145
    Prev
    Next
    INDEX
    Explanations

    healthy and

    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_16_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
     સ
    0.59
    の
    0.58
    嬲
    0.56
     დ
    0.56
    も
    0.56
    यक
    0.55
    गी
    0.53
    rahydro
    0.52
    의
    0.51
    Playing
    0.51
    POSITIVE LOGITS
    -
    0.57
    कन्या
    0.53
     "
    0.50
    igste
    0.50
     en
    0.50
    al
    0.49
     straighten
    0.48
     tou
    0.47
     get
    0.47
     undoubt
    0.46
    Activations Density 0.003%

    No Known Activations