© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8005
    Prev
    Next
    INDEX
    Explanations

    publication years and names

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

    French, other languages, academic contexts

    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_53_width_65k_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
     sunt
    0.45
    뇨
    0.40
     bagian
    0.39
    <unused100>
    0.38
     동일
    0.38
     기타
    0.38
     pekan
    0.38
     antiseptic
    0.38
    다면
    0.38
     sulph
    0.37
    POSITIVE LOGITS
     appré
    0.38
     Wörter
    0.37
    至少
    0.36
    Essentials
    0.36
    }^{+}$.
    0.36
    に対する
    0.35
    求解
    0.35
     predictability
    0.35
     competent
    0.34
    }$).
    0.34
    Activations Density 0.025%

    No Known Activations