© 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. 4796
    Prev
    Next
    INDEX
    Explanations

    structured lists and phrases

    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
    ⇩
    1.19
    preventDefault
    1.19
    只能
    1.11
     chromatography
    1.09
     prepayment
    1.08
    霜
    1.07
    itions
    1.07
     cautions
    1.06
    ⤷
    1.06
    orney
    1.04
    POSITIVE LOGITS
    ichi
    1.34
    lang
    1.23
    運行
    1.22
     connexion
    1.21
     bich
    1.17
     uitvo
    1.16
     אז
    1.16
     heraus
    1.14
    وش
    1.13
     Transport
    1.12
    Activations Density 0.008%

    No Known Activations