© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199500
    Prev
    Next
    INDEX
    Explanations

    conditional clauses and continuations

    np_acts-logits-general · gemini-2.5-flash-lite

    * followed by details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     bananas
    0.56
     implement
    0.46
     телевиде
    0.45
     bullied
    0.45
     bitcoins
    0.45
     epilept
    0.44
     simpler
    0.44
    ]}$
    0.44
     telenov
    0.44
     husbands
    0.43
    POSITIVE LOGITS
    selective
    0.46
    initialized
    0.46
    resulting
    0.44
     கிட
    0.43
    ải
    0.42
    ینده
    0.42
    affiliation
    0.42
    awaited
    0.42
    IMENT
    0.41
    Endian
    0.41
    Activations Density 0.000%

    No Known Activations