© 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. 116905
    Prev
    Next
    INDEX
    Explanations

    his opponents

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

    ** elements fields upload embarrassed

    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
    }//
    0.50
     consequ
    0.49
    ]。
    0.47
     قاسمی
    0.45
     prij
    0.45
    seqNum
    0.43
    </h4>
    0.43
     múlti
    0.43
    sequelize
    0.42
     Objet
    0.42
    POSITIVE LOGITS
    ہ
    0.46
    ینس
    0.46
    ety
    0.44
    ys
    0.44
    ank
    0.44
    edes
    0.44
     Updated
    0.43
     Candidate
    0.43
    ange
    0.42
    acy
    0.42
    Activations Density 0.000%

    No Known Activations