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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106805
    Prev
    Next
    INDEX
    Explanations

    not necessarily

    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
    probably
    -1.48
    almost
    -1.41
     både
    -1.38
     довольно
    -1.33
     pretty
    -1.27
    both
    -1.26
    かなり
    -1.23
    BOTH
    -1.23
     probablement
    -1.22
     zarówno
    -1.22
    POSITIVE LOGITS
     necessarily
    2.94
     or
    2.06
     necesariamente
    1.93
    necessarily
    1.92
     any
    1.85
     necessariamente
    1.53
     anything
    1.49
     quelconque
    1.42
    有任何
    1.41
     suddenly
    1.37
    Activations Density 0.060%

    No Known Activations