© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5914
    Prev
    Next
    INDEX
    Explanations

    why did

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    '?
    2.49
    ’?
    2.35
    ?'
    2.28
    }?
    2.27
    ?’”
    2.25
    '&
    2.25
    ?’
    2.24
     ifs
    2.19
     ล่ะ
    2.14
     willst
    2.13
    POSITIVE LOGITS
    ravés
    1.44
    主に
    1.33
    elos
    1.27
    rieben
    1.25
    ato
    1.22
     ([
    1.21
     Throat
    1.21
    hetamine
    1.20
     ((
    1.18
    rime
    1.18
    Activations Density 0.060%

    No Known Activations