© 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. 224188
    Prev
    Next
    INDEX
    Explanations

    destroyed by, child responds, rise view

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

    but, If, mirroring, framed, geared, tailored

    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
    ዋ
    0.49
    ファ
    0.47
    곳
    0.45
    ό
    0.44
    우리
    0.43
    峹
    0.43
     család
    0.43
    زندگی
    0.42
    说过
    0.42
    언
    0.41
    POSITIVE LOGITS
     Randomized
    0.45
     sehe
    0.43
     randomIndex
    0.43
     proposte
    0.42
     preguntar
    0.42
     randomized
    0.41
     ramus
    0.41
    drawing
    0.41
    uri
    0.41
    ruck
    0.40
    Activations Density 0.000%

    No Known Activations