© 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. 78579
    Prev
    Next
    INDEX
    Explanations

    occasionally, periodically, from

    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
     solito
    -0.92
     selalu
    -0.92
     subito
    -0.85
    foreground
    -0.84
     nisi
    -0.83
    Ⓣ
    -0.83
     sempre
    -0.83
    
    -0.83
     always
    -0.82
    大多
    -0.82
    POSITIVE LOGITS
     from
    4.34
     occasionally
    2.61
    From
    2.33
     From
    2.31
    from
    2.09
     periodically
    2.03
    occasion
    1.99
    Occasionally
    1.96
     từ
    1.89
    从
    1.89
    Activations Density 0.057%

    No Known Activations