© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116586
    Prev
    Next
    INDEX
    Explanations

    Personal statements of belief, hope, or action

    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
    oved
    -1.23
    mogen
    -1.19
     diretor
    -1.07
     from
    -1.03
     теперь
    -1.02
       
    -1.02
    -};
    -0.99
    enerys
    -0.99
    zzet
    -0.98
    ままで
    -0.98
    POSITIVE LOGITS
     also
    4.09
     также
    2.13
     would
    2.11
     even
    2.05
     however
    1.94
     know
    1.87
     também
    1.84
    Also
    1.79
     hope
    1.78
     guess
    1.78
    Activations Density 0.104%

    No Known Activations