© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7754
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other numbers/symbols

    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_262k_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
    ه
    0.28
     OPEC
    0.22
     orgasm
    0.21
    AfterTax
    0.21
    Sept
    0.20
     isom
    0.20
    িনবার্গ
    0.20
    Name
    0.20
     unisex
    0.20
     abstra
    0.20
    POSITIVE LOGITS
    nd
    0.37
    ಗಳು
    0.27
    ă
    0.26
    ної
    0.26
    x
    0.26
    at
    0.25
    ções
    0.24
    ၊
    0.24
     consistente
    0.24
    на
    0.23
    Activations Density 0.235%

    No Known Activations