© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1105
    Prev
    Next
    INDEX
    Explanations

    C++ output streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     consider
    0.93
     powers
    0.89
     Consider
    0.88
    ்
    0.85
     meh
    0.85
    ের
    0.83
     mal
    0.80
    യുടെ
    0.80
    𝘦
    0.79
    âne
    0.78
    POSITIVE LOGITS
    endl
    1.11
     endl
    0.97
    ··
    0.90
     constructor
    0.88
    ar
    0.84
    écriture
    0.83
    }*/
    0.83
     evid
    0.82
     учет
    0.82
     நடத்தி
    0.81
    Activations Density 0.019%

    No Known Activations