© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 30654
    Prev
    Next
    INDEX
    Explanations

    recalling and predicting future

    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_40_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
     amplitudes
    0.43
     Salman
    0.41
     CLIENTI
    0.39
    ಡುಗೆ
    0.39
    ப்போதும்
    0.38
    失去了
    0.38
     appliquée
    0.36
    𝟐
    0.36
    置いて
    0.36
    CENTR
    0.36
    POSITIVE LOGITS
    Owin
    0.44
    anim
    0.42
    Anim
    0.41
    Jug
    0.40
    abst
    0.39
    LC
    0.38
    ei
    0.38
    ender
    0.38
    сан
    0.38
    мова
    0.37
    Activations Density 0.000%

    No Known Activations