© 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. 113313
    Prev
    Next
    INDEX
    Explanations

    offers, many, Bush, embraces, required, needed, strategy

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

    Discuss FOUR (4)

    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
    🎍
    0.46
     insects
    0.45
    せい
    0.45
     vir
    0.42
     termites
    0.42
     speculated
    0.41
     pissed
    0.41
     irreversible
    0.40
     offered
    0.40
    气的
    0.40
    POSITIVE LOGITS
    iler
    0.54
    ate
    0.53
    adilla
    0.52
     r
    0.51
    gegevens
    0.51
    icación
    0.50
    illet
    0.50
    letos
    0.50
    <0xBA>
    0.49
     и
    0.49
    Activations Density 0.001%

    No Known Activations