© 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. 231386
    Prev
    Next
    INDEX
    Explanations

    immediate telephone call

    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
    掍
    0.49
    បែប
    0.48
    тное
    0.46
    ការពារ
    0.46
    }]$,
    0.43
     يَ
    0.42
    簪
    0.42
     Hate
    0.42
    وفر
    0.42
    }}}=
    0.42
    POSITIVE LOGITS
    Billing
    0.43
     лю
    0.43
    endif
    0.43
    Custodian
    0.42
     alternatif
    0.42
     acquis
    0.42
    лум
    0.42
    andas
    0.41
     refining
    0.41
     Бере
    0.41
    Activations Density 0.001%

    No Known Activations