© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 149637
    Prev
    Next
    INDEX
    Explanations

    USAM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     ].
    0.93
     $)$.
    0.89
     hotel
    0.83
     $-$
    0.82
     isn
    0.82
     dean
    0.82
     ).
    0.80
    .].
    0.79
     aren
    0.78
    ]).
    0.74
    POSITIVE LOGITS
    গণের
    0.92
    ുള്ള
    0.92
    だけの
    0.81
    のための
    0.80
    證據
    0.79
    的部分
    0.78
     ಹೊಂದಿದೆ
    0.78
    品
    0.78
     المهم
    0.77
    たちの
    0.77
    Activations Density 0.003%

    No Known Activations