© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60884
    Prev
    Next
    INDEX
    Explanations

    self, (, )

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deline
    -0.88
     demar
    -0.84
     poë
    -0.82
    Deel
    -0.82
    Tipps
    -0.81
    Zubereitung
    -0.81
    杢
    -0.79
    剛剛
    -0.79
     gouverneur
    -0.78
    看去
    -0.78
    POSITIVE LOGITS
     *
    1.66
    *
    1.22
     **
    1.12
    **
    1.12
     *=
    1.02
     }^{*}
    0.93
    (*
    0.89
    bry
    0.88
     wrapped
    0.88
    )*
    0.88
    Activations Density 0.016%

    No Known Activations