© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3661
    Prev
    Next
    INDEX
    Explanations

    probability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    rega
    0.49
    ingh
    0.49
    versa
    0.48
     wyniki
    0.46
    ğu
    0.46
    いです
    0.45
     utilizza
    0.44
    腩
    0.43
    }$}
    0.40
    ):\
    0.39
    POSITIVE LOGITS
     fucking
    1.90
     respir
    1.89
     imaginar
    1.84
     abducted
    1.80
     الإنسان
    1.77
     почув
    1.77
     oliv
    1.76
     kinda
    1.76
     imagining
    1.76
     evanescent
    1.75
    Activations Density 0.138%

    No Known Activations