© 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-65K
    7. 13256
    Prev
    Next
    INDEX
    Explanations

    options like all, none, cannot

    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_65k_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
     بڑے
    0.50
     downside
    0.45
     unsuccessful
    0.44
     downsides
    0.42
     anche
    0.42
     rewrite
    0.42
    ╹
    0.41
    ிடம்
    0.40
     دوسرا
    0.40
    বড়
    0.40
    POSITIVE LOGITS
     («
    0.45
     (“
    0.43
    -
    0.43
     этих
    0.42
    𝐜
    0.40
    都很
    0.39
    这个问题
    0.39
     (‘
    0.39
    ках
    0.39
    వచ్చు
    0.38
    Activations Density 0.062%

    No Known Activations