© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40606
    Prev
    Next
    INDEX
    Explanations

    interpolation factor. 0 returnsblend factor. 0 meansreturns q0, 1 returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    芋
    0.48
    ρο
    0.47
    ק
    0.47
    кар
    0.45
    ة
    0.45
     keyed
    0.44
     experts
    0.44
    чі
    0.44
    θυ
    0.44
    تون
    0.44
    POSITIVE LOGITS
     curva
    0.51
     paradigma
    0.51
     リン
    0.49
     jugador
    0.48
     Maugin
    0.48
     Reserva
    0.47
     supplier
    0.47
     Buon
    0.47
     Registro
    0.47
     ผ
    0.46
    Activations Density 0.002%

    No Known Activations