© 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. 57819
    Prev
    Next
    INDEX
    Explanations

    driving towards

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

    but Versus different

    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
    )}_
    0.44
     necessities
    0.42
    ゴー
    0.42
     bicovariant
    0.41
    はある
    0.41
    }));
    0.41
     estratégico
    0.40
     disadvant
    0.40
    ற்காக
    0.39
     lilac
    0.39
    POSITIVE LOGITS
     Current
    0.48
     此
    0.46
     THIS
    0.46
     Corporate
    0.44
    ►
    0.44
     SINGLE
    0.43
     Versus
    0.43
     当前
    0.42
    Current
    0.42
     Single
    0.42
    Activations Density 0.000%

    No Known Activations