© 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. 126434
    Prev
    Next
    INDEX
    Explanations

    describing states or following actions

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

    placeholder in text

    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
     significative
    0.55
    lal
    0.54
    ethi
    0.52
     skulls
    0.52
    ro
    0.50
    ę
    0.50
    ue
    0.49
    lah
    0.49
    lin
    0.49
     thigh
    0.49
    POSITIVE LOGITS
    的には
    0.55
    generally
    0.45
    ]}$
    0.44
    ٩
    0.44
    報酬
    0.41
    σ
    0.41
    ufieurs
    0.41
    Vendo
    0.41
    žiť
    0.40
    WebElement
    0.40
    Activations Density 0.000%

    No Known Activations