© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 557
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    1.75
     in
    1.63
     a
    1.61
     on
    1.59
     for
    1.50
     of
    1.49
    -
    1.42
     at
    1.41
     from
    1.39
     and
    1.38
    POSITIVE LOGITS
    𒁾
    2.28
    𒅕
    2.25
    𒆕
    2.25
    𒈲
    2.24
    𒀖
    2.24
    𒊓
    2.23
    𒀫
    2.23
    𒄖
    2.22
    𒌇
    2.22
    𒈩
    2.22
    Activations Density 2.653%

    No Known Activations